Multi-Pose Camera Motion Planning for Stacked Object Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion planning systems for robots in warehousing and retail environments rely on limited image information, leading to inaccurate object structure estimation and unreliable robot interactions, especially when objects are part of a stack, as they lack comprehensive views of object dimensions and structures.
Innovation Solution
A computing system that utilizes multiple camera poses and image information to generate accurate object structure estimates by capturing various viewpoints, including top and side views, to create a reliable motion plan for robot interaction, enabling precise object manipulation and de-palletization operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single camera pose is used for image capture, then the device complexity is reduced, but the measurement precision of object structure is insufficient
Solution Approach 1:
The system transitions from a single 2D camera view to multiple 2D views captured from different 3D positions and orientations. By coordinating the camera to capture images from multiple poses (different locations and orientations), the system gathers comprehensive spatial information that enables accurate 3D object structure estimation, resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The object structure estimation process is divided into multiple stages: first capturing images from an initial camera pose, then identifying additional viewpoints based on the first estimate, and finally capturing images from those additional poses. This segmented approach allows the system to build accurate structure estimates incrementally without requiring all camera poses to be predetermined, reducing overall system complexity
2Measurement precision
If multiple camera poses are used to capture comprehensive object views, then the measurement precision of object structure improves, but the loss of time increases
Solution Approach 1:
The system performs preliminary action by using the first image and first structure estimate to identify additional viewpoints before capturing the second set of images. This allows the system to plan the most efficient camera path in advance, capturing only the necessary views from optimally positioned angles, thereby reducing the total time required while maintaining high measurement precision
Solution Approach 2:
The system employs feedback by using the first structure estimate as input to determine the second camera pose. The output of the first estimation stage feeds into the planning of the second capture stage, creating an adaptive process that adjusts camera positioning based on previously gathered information. This feedback mechanism reduces redundant captures and optimizes the time required for comprehensive object structure estimation
Data Source
AI summary
A system and method for motion planning is presented. The system is configured, when an object is or has been in a camera field of view of a camera, to receive first image information that is generated when the camera has a first camera pose. The system is further configured to determine, based on the first image information, a first estimate of the object structure, and to identify, based on the first estimate of the object structure or based on the first image information, an object corner. The system is further configured to cause an end effector apparatus to move the camera to a second camera pose, and to receive second image information for representing the object's structure. The system is configured to determine a second estimate of the object's structure based on the second image information, and to generate a motion plan based on at least the second estimate.


